Prediction of positive pulmonary nodules based on machine learning algorithm combined with central carbon metabolism data.

BACKGROUND: Lung cancer causes a huge disease burden, and early detection of positive pulmonary nodules (PPNs) as an early sign of lung cancer is extremely important for effective intervention. It is necessary to develop PPNs risk recognizer based on machine learning algorithm combined with central carbon metabolomics. METHODS: The study included 2248 participants at high risk for lung cancer from the Ma'anshan Community Lung Cancer Screening cohort. The Least Absolute Shrinkage and Selection Operator (LASSO) was used to screen 18 central carbon-related metabolites in plasma, recursive feature elimination (RFE) was used to select all 42 features, followed by five machine learning algorithms for model development. The performance of the model was evaluated using area under the receiver operator characteristic curve (AUC), accuracy, precision, recall, and F1 scores. In addition, SHapley Additive exPlanations (SHAP) was performed to assess the interpretability of the final selected model and to gain insight into the impact of features on the predicted results. RESULTS: Finally, the two prediction models based on the random forest (RF) algorithm performed best, with AUC values of 0.87 and 0.83, respectively, better than other models. We found that homogentisic acid, fumaric acid, maleic acid, hippuric acid, gluconic acid, and succinic acid played a significant role in both PPNs prediction model and NPNs vs PPNs model, while 2-oxadipic acid only played a role in the former model and phosphopyruvate only played a role in the NPNs vs PPNs model. This model demonstrates the potential of central carbon metabolism for PPNs risk prediction and identification. CONCLUSION: We developed a series of predictive models for PPNs, which can help in the early detection of PPNs and thus reduce the risk of lung cancer.

Effect of exposures to multiple metals on blood pressure and hypertension in the elderly: a community-based study.

A chronic disease, hypertension (HTN) is prevalent among the elderly. Exploring the factors that influence HTN and blood pressure (BP) changes is of great public health significance. However, mixed exposure to multiple serum metals has had less research on the effects on BP and HTN for the elderly. From April to August 2019, 2372 people participated in the community physical examination program for the elderly in Tongling City, Anhui Province. We measured BP and serum levels of 10 metals and collected basic demographic information. We analyzed the relationship between metal levels and changes in BP and HTN by the least absolute shrinkage and selection operator regression, Bayesian kernel machine regression model, and generalized linear model. In multiple models, lead (Pb) and cadmium (Cd) were still significantly associated with HTN occurrence after adjusting for potential confounders (Pb: ORquartile 4 VS quartile 1 = 1.20, 95% CI 1.01-1.43; Cd: ORquartile 4 VS quartile 1 = 1.37, 95% CI 1.16-1.62). In the male subgroup, results were similar to those of the general population. In the female group, Cd was positively correlated with HTN and systolic blood pressure, while Pb was not. According to this study, Pb and Cd were correlated with BP and HTN positively, and there was a certain joint effect. To some extent, our findings provide clues for the prevention of hypertension in the elderly.

Targeted metabolomics reveals the association between central carbon metabolism and pulmonary nodules.

With the widespread application of low-dose computed tomography (LDCT) technology, pulmonary nodules have aroused more attention. Significant alteration in plasma metabolite levels, mainly amino acid and lipid, have been observed in patients of PNs. However, evidence on the association between central carbon metabolism and PNs are largely unknown. The aim of this study was to investigate the underlying association of PNs and plasma central carbon metabolites. We measured the levels of 16 plasma central carbon metabolites in 1954 participants who gained LDCT screening in MALSC cohort. The inverse probability weighting (IPW) technique was used to control for bias due to self-selection for LDCT in the assessed high-risk population. The least absolute shrinkage and selection operator (LASSO) penalized regression was used to deal with the problem of multicollinearity among metabolites and the combined association of central carbon metabolites with PNs was estimated by using quantile g-computation (QgC) models. A quartile increase in 3-hydroxybutyric acid, gluconic acid, succinic acid and hippuric acid was positively associated with the PNs risk, whereas a quartile increase in 2-oxadipic acid and fumaric acid was negatively associated with the risk of PNs in multiple-metabolite models. A positive but insignificant joint associations of the mixture of 16 metabolites with PNs was observed by using QgC models analyses. Further studies are warranted to clarify the association between circulating metabolites and PNs and the biological mechanisms.

The impact of multiple metals exposure on the risk of developing proliferative diabetic retinopathy in Anhui, China: a case-control study.

Through multiple different pathways, the environmental multiple metals make their ways to the human bodies, where they induce different levels of the oxidative stress response. This study further investigated the impact of multiple-metal exposure on the risk of developing proliferative diabetic retinopathy (PDR). We designed a case-control study with type 2 diabetic patients (T2D), in which the case group was the proliferative diabetic retinopathy group (PDR group), while the control group was the non-diabetic retinopathy group (NDR group). Graphite furnace atomic absorption spectrometry (GFAAS) and inductively coupled plasma optical emission spectrometry (ICP-OES) were used to detect the metal levels in our participants' urine samples. The least absolute shrinkage and selection operator (LASSO) regression approach was used to include these representative trace elements in a multiple exposure model. Following that, logistic regression models and Bayesian kernel machine regression (BKMR) models were used to describe the effect of different elements and also analyze their combined effect. In the single-element model, we discovered that lithium (Li), cadmium (Cd), and strontium (Sr) were all positively related to PDR. The multiple-exposure model revealed a positive relationship between Li and PDR risk, with a maximum quartile OR of 2.80 (95% CI: 1.10-7.16). The BKMR model also revealed that selenium (Se) might act as a protective agent, whereas magnesium (Mg), Li, and Cd may raise the risk of PDR. In conclusion, our study not only revealed an association between exposure to multiple metals and PDR risk but it also implied that urine samples might be a useful tool to assess PDR risk.

The combined effects of exposure to multiple PM2.5 components on overweight and obesity in middle-aged and older adults: a nationwide cohort study from 125 cities in China.

The prevalence of overweight or obesity increased rapidly over the past decades in most countries, including China. However, little evidence exists about the effects of long-term exposure to PM2.5 components on overweight or obesity, particularly in developing countries. We measured different weight stages according to body mass index (BMI), and investigated the effects of exposure to PM2.5 components (ammonium [[Formula: see text]], sulfate [[Formula: see text]], nitrate [[Formula: see text]], black carbon and organic matter) on different BMI levels in middle-aged and elderly people of China. Our study explored the effects of single and multiple air pollution exposures on overweight and obesity by using the Generalized Linear Model and Quantile g-Computation model (QgC). This study found a significantly positive association between five PM2.5 components and overweight/obesity. In the QgC model, there was still a positive association between multiple exposure to PM2.5 components and overweight when all PM2.5 components were considered as a whole. In addition, males, the elderly, and urban residents were also more sensitive to five PM2.5 components.

The impact of ambient air pollutants on childhood respiratory system disease and the resulting disease burden: a time-series study.

PURPOSE: The effects of air pollution on human health have long been a hot topic of research. For respiratory diseases, a large number of studies have proved that air pollution is one of the main causes. The purpose of this study was to investigate the risk of hospitalization of children with respiratory system diseases (CRSD) caused by six pollutants (PM2.5, PM10, NO2, SO2, CO, and O3) in Hefei City, and further calculate the disease burden. METHOD: In the first stage, the generalized additive models were combined with the distributed lag non-linear models to evaluate the impact of air pollution on the inpatients for CRSD in Hefei. In the second stage, this study used the cost-of-illness approach to calculate the attributable number of hospitalizations and the extra disease burden. RESULT: Overall, all the six kinds of pollutants had the strongest effects on CRSD inpatients within lag10 days. SO2 and CO caused the highest and lowest harm, respectively, and the RR values were SO2 (lag0-5): 1.1 20 (1.053, 1.191), and CO (lag0-6): 1.002 (1.001, 1.003). During the study period (January 1, 2014 to December 30, 2020), the 7-year cumulative burden of disease was 36.19 million CNY under the WHO air pollution standards. CONCLUSION: In general, we found that six air pollutants were risk factors for CRSD in Hefei City, and create a huge burden of disease.

Maternal exposure to extreme high-temperature, particulate air pollution and macrosomia in 14 countries of Africa.

BACKGROUND: Macrosomia has increased rapidly worldwide in the past few decades, with a huge impact on health. However, the effect of PM2.5 and extreme high-temperature (EHT) on macrosomia has been ignored. OBJECTIVE: This study aimed to explore the association between maternal exposure to EHT, PM2.5 and macrosomia based on the Seventh Demographic and Health Survey (DHS) in 14 countries of Africa. METHODS: The study included detailed demographic information on 106 382 births and maternal. Satellite inversion models estimated monthly mean PM2.5 and mean surface temperature of 2 m (SMT2m ). Macrosomia was defined as the birth weight ≥ 4000 g. We used a Cox proportional risk regression model to estimate the association between PM2.5 , EHT and macrosomia. We further explored the susceptibility of exposure to EHT and PM2.5 at different pregnancy periods to macrosomia, and plotted the expose-response curve between PM2.5 and macrosomia risk using a restricted cubic spline function. In addition, the Interplot model was used to investigate the interaction between EHT and PM2.5 on macrosomia. Finally, some potential confounding factors were analysed by stratification. RESULTS: There was the positive association between EHT, PM2.5 and macrosomia, and the risk of macrosomia with the increase in concentrations of PM2.5 without clear threshold. Meanwhile, EHT and PM2.5 had a higher effect on macrosomia in middle/later and early/middle stages of pregnancy, respectively. There was a significant interaction between EHT and PM2.5 on macrosomia. CONCLUSIONS: Maternal exposure to EHT, PM2.5 during pregnancy was associated with an increased risk of macrosomia in Africa.

Association of exposure to multiple serum metals with the risk of chronic kidney disease in the elderly: a population-based case-control study.

In the world, chronic kidney disease (CKD) has been recognized as one of the critical public health problems, and the prevalence is higher in the elderly people. However, there are few studies on the association between exposure to multiple serum metal levels and CKD. A case-control study, we established, for elderly people in Anhui Province, China, to explore the effects of different metals and analyze the effect of mixed exposure on CKD. In this study, 287 cases of CKD and 287 controls were selected in the elderly health physical examination project in Tongling City, Anhui Province. Questionnaire survey, physical examination, and blood collection were conducted. Graphite furnace atomic absorption spectrometry (GFAAS) and inductively coupled plasma optical emission spectrometry (ICP-OES) were used to measure the concentration of serum metals. After selecting by least absolute shrinkage and selection operator (LASSO), 5 metals were brought into the multi-metal model. After adjusting all potential covariates additionally, the concentrations of lead (Pb), cadmium (Cd), cobalt (Co), and manganese (Mn) were significantly associated with CKD risk, whereas Pb, Se, and Cd had significant non-linearity with CKD. Besides, patients with highest quartiles of cobalt (Co), lead (Pb), and manganese (Mn) were 1.64, 1.39, and 0.64 times more possible to have CKD, respectively, as compared with the lowest levels. In the Bayesian kernel machine regression (BKMR) model, cadmium (Cd) had a combined effect with lead (Pb) possibly. This study suggested that the CKD risk was associated with exposure of multiple metals in elderly people. The underlying mechanisms of serum metals and CKD need more experimental and prospective studies to elucidate.

Exposure to multiple trace elements and thyroid cancer risk in Chinese adults: A case-control study.

The incidence of thyroid cancer (TC) has increased rapidly in last decades. Multiple trace elements in the external environment have important effects with thyroid function. However, the evidence for these on TC risk were rarely reported. A total of 585 newly diagnosed TC patients and 585 healthy controls were included in this study, and 14 urinary elements were measured to explain the fixed-exposure effect on TC risk. Conditional logistic regressions were used to reflect the multi-element associations, and Bayesian kernel machine regression (BKMR) was applied to show the tendency of mixed effects. Furthermore, the interaction effects were examined by Generalized linear model (GLM). The levels of lithium (Li), cobalt (Co), strontium (Sr), zinc (Zn) and copper (Cu) had negative effects with TC risk, nevertheless lead (Pb), arsenic (As) and chromide (Cr) showed positive effects. The BKMR and GLM models reflected the effect fluctuations of different elements, and there was a slight interaction effects between Li and Cr, Co, Zn and Pb. Further study is required to confirm these results in the future.

Individual PM2.5 component exposure model, elevated blood pressure and hypertension in middle-aged and older adults: A nationwide cohort study from 125 cities in China.

Recently, elevated blood pressure (BP) and hypertension (HTN) have caused a huge burden of health loss. Previous studies used ambient air pollutants as a proxy for individual exposure, limiting the assessment of its multiple exposure to health effects. For the first time, this study constructed individual PM2.5 component (SO42-, NO3-, NH4+, OM, and BC) exposure model DAG (Directed Acyclic Graph), DAG-oriented generalized linear model and random forest model, and explored the effects of single and multiple exposures to PM2.5 components on BP at different stages by the generalized linear model (GLM) and Quantile g-Computation (QgC) model based on a large cohort study in China. We defined BP in four stages according to the 2017 ACC/AHA guidelines. After excluding the lack of key information, the cohort analyses ultimately included 9031 participants. Our results showed that the individual PM2.5 component exposure model had good efficacy. Single or multiple exposure to PM2.5 components had significant positive effects on normal BP to elevated BP and elevated BP to stage 1 HTN. In addition, males, the elderly and urban residents were more sensitive to PM2.5 components. This study provided implications for environmental exposure assessment and control of particulate pollution in the future.

Outdoor air pollution enhanced the association between indoor air pollution exposure and hypertension in rural areas of eastern China.

Recently, the high prevalence of hypertension (HTN) has caused serious disease burden. Previous studies mostly focused on the separate association between outdoor or indoor air pollution and HTN, and did not explore their possible interaction with HTN. To explore this issue, this study investigated the relationship between indoor and outdoor air pollution and HTN and their possible interactions among adult residents in 14 rural areas in eastern China. The generalized linear model (GLM) and interplot model were used to evaluate the separate effects and potential interaction of outdoor or indoor air pollutants on HTN. In separate analyses, we found a significant positive association between outdoor and indoor air pollution and HTN, and a significant negative association between range hood use and HTN. In the interaction analysis, outdoor air pollution could significantly enhance the positive effects of indoor air pollution on HTN. In addition, PM2.5 and O3 could significantly reduce the protective effect of range hoods use on HTN. Finally, we found that females were more susceptible to both indoor and outdoor air pollution.

Associations between environmental exposure to polybrominated diphenyl ethers and nodular goiter risk: A case-control study.

Polybrominated diphenyl ethers (PBDEs) are widespread and persistent environmental contaminants, but their association with nodular goiter (NG) remains unknown. The present case-control study of 179 NG cases and 358 matched normal controls aimed to investigate the association between PBDEs and risk of NG. The plasma concentrations of 8 PBDEs congeners (BDE-28, -47, -99, -100, -153, -154, -183, and -209) were determined by gas chromatograph-mass spectrometer. Conditional logistic regression model was used to evaluate the odds ratio (OR) and 95% confidence interval (CI) for the association between each PBDEs congener and NG. Bayesian kernel machine regression (BKMR) was used to evaluate the association between overall levels of 8 PBDEs mixture and NG. The results of logistic model suggested that increased risk of NG was associated with elevated concentrations of all PBDEs congeners, except for BDE-209. In BKMR model, the risk of NG increased with the increase in overall exposure level of 8 PBDEs mixture. Compared to when all PBDEs mixture were at their median value, the risk of exposure-response function for NG increased by 0.34 units when all PBDEs were at their 75th percentile. In women, the results showed similar trends after additional adjustment for age at menarche and menopausal status. These findings provide novel epidemiological evidence for the prevention of NG. However, larger prospective studies are required to address the associations between PBDEs exposure and NG risk.

Multiple environmental exposures and obesity in eastern China: An individual exposure evaluation model.

Obesity has caused a huge burden of disease. Few studies have explored individuals' environmental exposure level and the impact of multiple environmental exposures on obesity. The aim of this study was to explore individual air pollution exposure evaluation, and the association between and multiple environmental factors and obesity among adult residents in rural areas of China. In this study, 8400 residents of 14 districts and counties in eastern of China were selected by multistage stratified cluster sampling, and a total of 8377 residents were included in the final analysis. We adopted BMI (Body Mass Index) > 28 kg/m2 as the definition of obesity. First, an individual air pollution evaluation model was established based on the monitoring data of air pollution stations closest to residential address, different demographic characteristics of residents and daily living habits using generalized linear model and random forest model. Then, we used Bayesian Kernel Machine Regression (BKMR) and Quantile g-Computation (QgC) models to explore multiple environmental exposures on obesity. The results showed that six air pollutants were significantly positively associated with obesity, and green space had a significant protective effect on obesity. The BKMR model showed that the effects of different air pollutants on obesity were significantly enhanced by each other, while green space significantly reduced the positive effect of air pollution on obesity. The QgC model showed a significant positive association with obesity when all environmental factors were exposed as a whole, especially in males, higher household incomes and young people. It suggested that relevant authorities should improve regional air quality and green space to reduce the burden of disease caused by obesity.

Application and development of palm print research.

The palm print contains a great deal of information which is of great research and application value. This paper provides palm print research methods, application, and the relationship between the palm print and cancer.